SOTAVerified

Network Pruning

Network Pruning is a popular approach to reduce a heavy network to obtain a light-weight form by removing redundancy in the heavy network. In this approach, a complex over-parameterized network is first trained, then pruned based on come criterions, and finally fine-tuned to achieve comparable performance with reduced parameters.

Source: Ensemble Knowledge Distillation for Learning Improved and Efficient Networks

Papers

Showing 125 of 534 papers

TitleStatusHype
Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum0
TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks0
Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language ModelsCode0
Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the EdgeCode0
Bi-LSTM based Multi-Agent DRL with Computation-aware Pruning for Agent Twins Migration in Vehicular Embodied AI Networks0
Guiding Evolutionary AutoEncoder Training with Activation-Based Pruning OperatorsCode0
ReplaceMe: Network Simplification via Layer Pruning and Linear TransformationsCode1
Optimization over Trained (and Sparse) Neural Networks: A Surrogate within a Surrogate0
Hyperflows: Pruning Reveals the Importance of Weights0
Boosting Large Language Models with Mask Fine-TuningCode0
Lipschitz Constant Meets Condition Number: Learning Robust and Compact Deep Neural Networks0
Maximum Redundancy Pruning: A Principle-Driven Layerwise Sparsity Allocation for LLMs0
Finding Stable Subnetworks at Initialization with Dataset Distillation0
Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systems0
Signal Collapse in One-Shot Pruning: When Sparse Models Fail to Distinguish Neural Representations0
NTP-INT: Network Traffic Prediction-Driven In-band Network Telemetry for High-load Switches0
An Efficient Row-Based Sparse Fine-Tuning0
Automatic Pruning via Structured Lasso with Class-wise Information0
Exploring Neural Network Pruning with Screening Methods0
B-FPGM: Lightweight Face Detection via Bayesian-Optimized Soft FPGM PruningCode0
Compact Bayesian Neural Networks via pruned MCMC samplingCode0
Neural Architecture Codesign for Fast Physics ApplicationsCode0
Exploring GLU Expansion Ratios: A Study of Structured Pruning in LLaMA-3.2 ModelsCode5
Scalable iterative pruning of large language and vision models using block coordinate descent0
Adapting the Biological SSVEP Response to Artificial Neural Networks0
Show:102550
← PrevPage 1 of 22Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50-2.3 GFLOPsAccuracy78.79Unverified
2ResNet50-1.5 GFLOPsAccuracy78.07Unverified
3ResNet50 2.5 GFLOPSAccuracy78Unverified
4RegX-1.6GAccuracy77.97Unverified
5ResNet50 2.0 GFLOPSAccuracy77.7Unverified
6ResNet50-3G FLOPsAccuracy77.1Unverified
7ResNet50-2G FLOPsAccuracy76.4Unverified
8ResNet50-1G FLOPsAccuracy76.38Unverified
9TAS-pruned ResNet-50Accuracy76.2Unverified
10ResNet50Accuracy75.59Unverified
#ModelMetricClaimedVerifiedStatus
1FeatherTop-1 Accuracy76.93Unverified
2SpartanTop-1 Accuracy76.17Unverified
3ST-3Top-1 Accuracy76.03Unverified
4AC/DCTop-1 Accuracy75.64Unverified
5CSTop-1 Accuracy75.5Unverified
6ProbMaskTop-1 Accuracy74.68Unverified
7STRTop-1 Accuracy74.31Unverified
8DNWTop-1 Accuracy74Unverified
9GMPTop-1 Accuracy73.91Unverified
#ModelMetricClaimedVerifiedStatus
1+U-DML*Inference Time (ms)675.56Unverified
2DenseAccuracy79Unverified
3AC/DCAccuracy78.2Unverified
4Beta-RankAccuracy74.01Unverified
5TAS-pruned ResNet-110Accuracy73.16Unverified
#ModelMetricClaimedVerifiedStatus
1TAS-pruned ResNet-110Accuracy94.33Unverified
2ShuffleNet – QuantisedInference Time (ms)23.15Unverified
3AlexNet – QuantisedInference Time (ms)5.23Unverified
4MobileNet – QuantisedInference Time (ms)4.74Unverified
#ModelMetricClaimedVerifiedStatus
1FFN-ShapleyPrunedAvg #Steps12.05Unverified